Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words indicating processes or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.50
     snippetHide
    -0.49
     ciudadana
    -0.47
    GraphicsUnit
    -0.46
    addContainerGap
    -0.46
    UserScript
    -0.46
     jScrollPane
    -0.45
    ArgumentParser
    -0.44
    Personendaten
    -0.44
    TagHelper
    -0.43
    POSITIVE LOGITS
    Tikang
    0.54
    ″]
    0.52
     Tully
    0.51
    hili
    0.49
    ogy
    0.49
    Usa
    0.48
    ORO
    0.48
     also
    0.47
    inty
    0.47
    rai
    0.46
    Act Density 0.856%

    No Known Activations